Modern condition monitoring-based methods are used to reduce maintenance costs, increase aircraft safety, and reduce fuel consumption. In the literature, parameters such as engine fan speeds, vibration, oil pressure, oil temperature, exhaust gas temperature (EGT), and fuel flow are used to determine performance deterioration in gas turbine engines. In this study, a new model was developed to get information about the gas turbine engine's condition. For this model, multiple regression analysis was carried out to determine the effect of the flight parameters on the EGT parameter and the artificial neural network (ANN) method was used in the identification of EGT parameter. At the end of the study, a network that predicts the EGT parameter with the smallest margin of error has been developed.

Purpose With the condition monitoring system on airplanes, failures can be predicted before they occur. Performance deterioration of aircraft engines is monitored by parameters such as fuel flow, exhaust gas temperature, engine fan speeds, vibration, oil pressure and oil temperature. The vibration parameter allows us to easily detect any existing or possible faults. The purpose of this paper is to develop a new model to estimate the low pressure turbine (LPT) vibration parameter of an aircraft engine by using the data of an aircraft’s actual flight from flight data recorder (FDR). Design/methodology/approach First, statistical regression analysis is used to determine the parameters related to LPT. Then, the selected parameters were applied as an input to the developed Levenberg–Marquardt feedforward neural network and the output LPT vibration parameter was estimated with a small error. Analyses were performed on MATLAB and SPSS Statistics 22 package program. Finally, the confidence interval method is used to check the accuracy of the estimated results of artificial neural networks (ANNs). Findings This study shows that the health conditions of an aircraft engine can be evaluated in terms of this paper by using confidence interval prediction of ANN-estimated LPT vibration parameters without dismantling and expert knowledge. Practical implications With this study, it has been shown that faults that may occur during flight can be easily detected using the data of a flight without expert evaluation. Originality/value The health condition of the turbofan engine was evaluated using the confidence interval prediction of ANN-estimated LPT vibration parameters.

No abstract